Linux premium82.web-hosting.com 4.18.0-553.44.1.lve.el8.x86_64 #1 SMP Thu Mar 13 14:29:12 UTC 2025 x86_64
LiteSpeed
Server IP : 185.61.154.194 & Your IP : 216.73.216.75
Domains :
Cant Read [ /etc/named.conf ]
User : evicodqw
Terminal
Auto Root
Create File
Create Folder
Localroot Suggester
Backdoor Destroyer
Readme
/
opt /
alt /
alt-nodejs22 /
root /
usr /
include /
unicode /
Delete
Unzip
Name
Size
Permission
Date
Action
alphaindex.h
26.54
KB
-rw-r--r--
2025-06-06 11:26
appendable.h
8.54
KB
-rw-r--r--
2025-06-06 11:26
basictz.h
9.99
KB
-rw-r--r--
2025-06-06 11:26
brkiter.h
27.84
KB
-rw-r--r--
2025-06-06 11:26
bytestream.h
10.77
KB
-rw-r--r--
2025-06-06 11:26
bytestrie.h
20.83
KB
-rw-r--r--
2025-06-06 11:26
bytestriebuilder.h
7.48
KB
-rw-r--r--
2025-06-06 11:26
calendar.h
107.54
KB
-rw-r--r--
2025-06-06 11:26
caniter.h
7.53
KB
-rw-r--r--
2025-06-06 11:26
casemap.h
25.42
KB
-rw-r--r--
2025-06-06 11:26
char16ptr.h
10.79
KB
-rw-r--r--
2025-06-06 11:26
chariter.h
23.79
KB
-rw-r--r--
2025-06-06 11:26
choicfmt.h
23.99
KB
-rw-r--r--
2025-06-06 11:26
coleitr.h
13.78
KB
-rw-r--r--
2025-06-06 11:26
coll.h
59.6
KB
-rw-r--r--
2025-06-06 11:26
compactdecimalformat.h
6.88
KB
-rw-r--r--
2025-06-06 11:26
curramt.h
3.67
KB
-rw-r--r--
2025-06-06 11:26
currpinf.h
7.3
KB
-rw-r--r--
2025-06-06 11:26
currunit.h
4.02
KB
-rw-r--r--
2025-06-06 11:26
datefmt.h
40.7
KB
-rw-r--r--
2025-06-06 11:26
dbbi.h
1.19
KB
-rw-r--r--
2025-06-06 11:26
dcfmtsym.h
20.96
KB
-rw-r--r--
2025-06-06 11:26
decimfmt.h
87.46
KB
-rw-r--r--
2025-06-06 11:26
displayoptions.h
7.08
KB
-rw-r--r--
2025-06-06 11:26
docmain.h
7.6
KB
-rw-r--r--
2025-06-06 11:26
dtfmtsym.h
38.22
KB
-rw-r--r--
2025-06-06 11:26
dtintrv.h
3.84
KB
-rw-r--r--
2025-06-06 11:26
dtitvfmt.h
48.87
KB
-rw-r--r--
2025-06-06 11:26
dtitvinf.h
18.63
KB
-rw-r--r--
2025-06-06 11:26
dtptngen.h
28.05
KB
-rw-r--r--
2025-06-06 11:26
dtrule.h
8.66
KB
-rw-r--r--
2025-06-06 11:26
edits.h
20.74
KB
-rw-r--r--
2025-06-06 11:26
enumset.h
2.08
KB
-rw-r--r--
2025-06-06 11:26
errorcode.h
4.84
KB
-rw-r--r--
2025-06-06 11:26
fieldpos.h
8.69
KB
-rw-r--r--
2025-06-06 11:26
filteredbrk.h
5.37
KB
-rw-r--r--
2025-06-06 11:26
fmtable.h
24.37
KB
-rw-r--r--
2025-06-06 11:26
format.h
12.51
KB
-rw-r--r--
2025-06-06 11:26
formattednumber.h
6.28
KB
-rw-r--r--
2025-06-06 11:26
formattedvalue.h
9.75
KB
-rw-r--r--
2025-06-06 11:26
fpositer.h
3.03
KB
-rw-r--r--
2025-06-06 11:26
gender.h
3.35
KB
-rw-r--r--
2025-06-06 11:26
gregocal.h
30.32
KB
-rw-r--r--
2025-06-06 11:26
icudataver.h
1.02
KB
-rw-r--r--
2025-06-06 11:26
icuplug.h
12.1
KB
-rw-r--r--
2025-06-06 11:26
idna.h
12.93
KB
-rw-r--r--
2025-06-06 11:26
listformatter.h
8.59
KB
-rw-r--r--
2025-06-06 11:26
localebuilder.h
11.08
KB
-rw-r--r--
2025-06-06 11:26
localematcher.h
26.86
KB
-rw-r--r--
2025-06-06 11:26
localpointer.h
19.55
KB
-rw-r--r--
2025-06-06 11:26
locdspnm.h
7.12
KB
-rw-r--r--
2025-06-06 11:26
locid.h
48.62
KB
-rw-r--r--
2025-06-06 11:26
measfmt.h
11.41
KB
-rw-r--r--
2025-06-06 11:26
measunit.h
111.44
KB
-rw-r--r--
2025-06-06 11:26
measure.h
4.63
KB
-rw-r--r--
2025-06-06 11:26
messageformat2.h
21.05
KB
-rw-r--r--
2025-06-06 11:26
messageformat2_arguments.h
4.49
KB
-rw-r--r--
2025-06-06 11:26
messageformat2_data_model.h
101.89
KB
-rw-r--r--
2025-06-06 11:26
messageformat2_data_model_names.h
784
B
-rw-r--r--
2025-06-06 11:26
messageformat2_formattable.h
38.36
KB
-rw-r--r--
2025-06-06 11:26
messageformat2_function_registry.h
18.07
KB
-rw-r--r--
2025-06-06 11:26
messagepattern.h
33.79
KB
-rw-r--r--
2025-06-06 11:26
msgfmt.h
44.2
KB
-rw-r--r--
2025-06-06 11:26
normalizer2.h
34.68
KB
-rw-r--r--
2025-06-06 11:26
normlzr.h
30.79
KB
-rw-r--r--
2025-06-06 11:26
nounit.h
2.24
KB
-rw-r--r--
2025-06-06 11:26
numberformatter.h
90.69
KB
-rw-r--r--
2025-06-06 11:26
numberrangeformatter.h
26
KB
-rw-r--r--
2025-06-06 11:26
numfmt.h
50.16
KB
-rw-r--r--
2025-06-06 11:26
numsys.h
7.22
KB
-rw-r--r--
2025-06-06 11:26
parseerr.h
3.08
KB
-rw-r--r--
2025-06-06 11:26
parsepos.h
5.56
KB
-rw-r--r--
2025-06-06 11:26
platform.h
27.18
KB
-rw-r--r--
2025-06-06 11:26
plurfmt.h
25.07
KB
-rw-r--r--
2025-06-06 11:26
plurrule.h
20.63
KB
-rw-r--r--
2025-06-06 11:26
ptypes.h
2.16
KB
-rw-r--r--
2025-06-06 11:26
putil.h
6.32
KB
-rw-r--r--
2025-06-06 11:26
rbbi.h
32.04
KB
-rw-r--r--
2025-06-06 11:26
rbnf.h
56.16
KB
-rw-r--r--
2025-06-06 11:26
rbtz.h
15.75
KB
-rw-r--r--
2025-06-06 11:26
regex.h
84.45
KB
-rw-r--r--
2025-06-06 11:26
region.h
9.2
KB
-rw-r--r--
2025-06-06 11:26
reldatefmt.h
22.48
KB
-rw-r--r--
2025-06-06 11:26
rep.h
9.38
KB
-rw-r--r--
2025-06-06 11:26
resbund.h
18.02
KB
-rw-r--r--
2025-06-06 11:26
schriter.h
6.09
KB
-rw-r--r--
2025-06-06 11:26
scientificnumberformatter.h
6.44
KB
-rw-r--r--
2025-06-06 11:26
search.h
22.21
KB
-rw-r--r--
2025-06-06 11:26
selfmt.h
14.35
KB
-rw-r--r--
2025-06-06 11:26
simpleformatter.h
12.6
KB
-rw-r--r--
2025-06-06 11:26
simplenumberformatter.h
8.87
KB
-rw-r--r--
2025-06-06 11:26
simpletz.h
45.62
KB
-rw-r--r--
2025-06-06 11:26
smpdtfmt.h
57.06
KB
-rw-r--r--
2025-06-06 11:26
sortkey.h
11.13
KB
-rw-r--r--
2025-06-06 11:26
std_string.h
1.05
KB
-rw-r--r--
2025-06-06 11:26
strenum.h
9.96
KB
-rw-r--r--
2025-06-06 11:26
stringoptions.h
5.79
KB
-rw-r--r--
2025-06-06 11:26
stringpiece.h
10.28
KB
-rw-r--r--
2025-06-06 11:26
stringtriebuilder.h
15.53
KB
-rw-r--r--
2025-06-06 11:26
stsearch.h
21.43
KB
-rw-r--r--
2025-06-06 11:26
symtable.h
4.28
KB
-rw-r--r--
2025-06-06 11:26
tblcoll.h
36.96
KB
-rw-r--r--
2025-06-06 11:26
timezone.h
45.59
KB
-rw-r--r--
2025-06-06 11:26
tmunit.h
3.4
KB
-rw-r--r--
2025-06-06 11:26
tmutamt.h
4.9
KB
-rw-r--r--
2025-06-06 11:26
tmutfmt.h
7.42
KB
-rw-r--r--
2025-06-06 11:26
translit.h
65.81
KB
-rw-r--r--
2025-06-06 11:26
tzfmt.h
42.95
KB
-rw-r--r--
2025-06-06 11:26
tznames.h
16.85
KB
-rw-r--r--
2025-06-06 11:26
tzrule.h
34.81
KB
-rw-r--r--
2025-06-06 11:26
tztrans.h
6.11
KB
-rw-r--r--
2025-06-06 11:26
ubidi.h
89.61
KB
-rw-r--r--
2025-06-06 11:26
ubiditransform.h
12.71
KB
-rw-r--r--
2025-06-06 11:26
ubrk.h
24.43
KB
-rw-r--r--
2025-06-06 11:26
ucal.h
63.96
KB
-rw-r--r--
2025-06-06 11:26
ucasemap.h
15.27
KB
-rw-r--r--
2025-06-06 11:26
ucat.h
5.35
KB
-rw-r--r--
2025-06-06 11:26
uchar.h
151.74
KB
-rw-r--r--
2025-06-06 11:26
ucharstrie.h
22.59
KB
-rw-r--r--
2025-06-06 11:26
ucharstriebuilder.h
7.48
KB
-rw-r--r--
2025-06-06 11:26
uchriter.h
13.24
KB
-rw-r--r--
2025-06-06 11:26
uclean.h
11.21
KB
-rw-r--r--
2025-06-06 11:26
ucnv.h
83.34
KB
-rw-r--r--
2025-06-06 11:26
ucnv_cb.h
6.58
KB
-rw-r--r--
2025-06-06 11:26
ucnv_err.h
20.98
KB
-rw-r--r--
2025-06-06 11:26
ucnvsel.h
6.24
KB
-rw-r--r--
2025-06-06 11:26
ucol.h
67.28
KB
-rw-r--r--
2025-06-06 11:26
ucoleitr.h
9.82
KB
-rw-r--r--
2025-06-06 11:26
uconfig.h
12.56
KB
-rw-r--r--
2025-06-06 11:26
ucpmap.h
5.54
KB
-rw-r--r--
2025-06-06 11:26
ucptrie.h
22.51
KB
-rw-r--r--
2025-06-06 11:26
ucsdet.h
14.69
KB
-rw-r--r--
2025-06-06 11:26
ucurr.h
16.72
KB
-rw-r--r--
2025-06-06 11:26
udat.h
62.36
KB
-rw-r--r--
2025-06-06 11:26
udata.h
15.63
KB
-rw-r--r--
2025-06-06 11:26
udateintervalformat.h
11.93
KB
-rw-r--r--
2025-06-06 11:26
udatpg.h
30.13
KB
-rw-r--r--
2025-06-06 11:26
udisplaycontext.h
5.94
KB
-rw-r--r--
2025-06-06 11:26
udisplayoptions.h
8.86
KB
-rw-r--r--
2025-06-06 11:26
uenum.h
7.79
KB
-rw-r--r--
2025-06-06 11:26
ufieldpositer.h
4.41
KB
-rw-r--r--
2025-06-06 11:26
uformattable.h
10.97
KB
-rw-r--r--
2025-06-06 11:26
uformattednumber.h
8.09
KB
-rw-r--r--
2025-06-06 11:26
uformattedvalue.h
12.25
KB
-rw-r--r--
2025-06-06 11:26
ugender.h
2.06
KB
-rw-r--r--
2025-06-06 11:26
uidna.h
34.12
KB
-rw-r--r--
2025-06-06 11:26
uiter.h
22.75
KB
-rw-r--r--
2025-06-06 11:26
uldnames.h
10.48
KB
-rw-r--r--
2025-06-06 11:26
ulistformatter.h
10.78
KB
-rw-r--r--
2025-06-06 11:26
uloc.h
55.38
KB
-rw-r--r--
2025-06-06 11:26
ulocale.h
6.31
KB
-rw-r--r--
2025-06-06 11:26
ulocbuilder.h
16.69
KB
-rw-r--r--
2025-06-06 11:26
ulocdata.h
11.3
KB
-rw-r--r--
2025-06-06 11:26
umachine.h
14.59
KB
-rw-r--r--
2025-06-06 11:26
umisc.h
1.34
KB
-rw-r--r--
2025-06-06 11:26
umsg.h
24.25
KB
-rw-r--r--
2025-06-06 11:26
umutablecptrie.h
8.3
KB
-rw-r--r--
2025-06-06 11:26
unifilt.h
4
KB
-rw-r--r--
2025-06-06 11:26
unifunct.h
4.05
KB
-rw-r--r--
2025-06-06 11:26
unimatch.h
6.1
KB
-rw-r--r--
2025-06-06 11:26
unirepl.h
3.38
KB
-rw-r--r--
2025-06-06 11:26
uniset.h
70.4
KB
-rw-r--r--
2025-06-06 11:26
unistr.h
182.08
KB
-rw-r--r--
2025-06-06 11:26
unorm.h
20.55
KB
-rw-r--r--
2025-06-06 11:26
unorm2.h
25.66
KB
-rw-r--r--
2025-06-06 11:26
unum.h
55.16
KB
-rw-r--r--
2025-06-06 11:26
unumberformatter.h
19.68
KB
-rw-r--r--
2025-06-06 11:26
unumberoptions.h
5.23
KB
-rw-r--r--
2025-06-06 11:26
unumberrangeformatter.h
15.35
KB
-rw-r--r--
2025-06-06 11:26
unumsys.h
7.26
KB
-rw-r--r--
2025-06-06 11:26
uobject.h
10.66
KB
-rw-r--r--
2025-06-06 11:26
upluralrules.h
8.79
KB
-rw-r--r--
2025-06-06 11:26
uregex.h
71.99
KB
-rw-r--r--
2025-06-06 11:26
uregion.h
9.81
KB
-rw-r--r--
2025-06-06 11:26
ureldatefmt.h
16.98
KB
-rw-r--r--
2025-06-06 11:26
urename.h
141.99
KB
-rw-r--r--
2025-06-06 11:26
urep.h
5.38
KB
-rw-r--r--
2025-06-06 11:26
ures.h
36.65
KB
-rw-r--r--
2025-06-06 11:26
uscript.h
28.51
KB
-rw-r--r--
2025-06-06 11:26
usearch.h
39.21
KB
-rw-r--r--
2025-06-06 11:26
uset.h
63.08
KB
-rw-r--r--
2025-06-06 11:26
usetiter.h
9.63
KB
-rw-r--r--
2025-06-06 11:26
ushape.h
18
KB
-rw-r--r--
2025-06-06 11:26
usimplenumberformatter.h
7.31
KB
-rw-r--r--
2025-06-06 11:26
uspoof.h
80
KB
-rw-r--r--
2025-06-06 11:26
usprep.h
8.19
KB
-rw-r--r--
2025-06-06 11:26
ustdio.h
38.58
KB
-rw-r--r--
2025-06-06 11:26
ustream.h
1.89
KB
-rw-r--r--
2025-06-06 11:26
ustring.h
72.16
KB
-rw-r--r--
2025-06-06 11:26
ustringtrie.h
3.15
KB
-rw-r--r--
2025-06-06 11:26
utext.h
58.1
KB
-rw-r--r--
2025-06-06 11:26
utf.h
7.87
KB
-rw-r--r--
2025-06-06 11:26
utf16.h
23.35
KB
-rw-r--r--
2025-06-06 11:26
utf32.h
763
B
-rw-r--r--
2025-06-06 11:26
utf8.h
30.83
KB
-rw-r--r--
2025-06-06 11:26
utf_old.h
45.8
KB
-rw-r--r--
2025-06-06 11:26
utmscale.h
13.78
KB
-rw-r--r--
2025-06-06 11:26
utrace.h
17.18
KB
-rw-r--r--
2025-06-06 11:26
utrans.h
25.54
KB
-rw-r--r--
2025-06-06 11:26
utypes.h
34.48
KB
-rw-r--r--
2025-06-06 11:26
uvernum.h
6.33
KB
-rw-r--r--
2025-06-06 11:26
uversion.h
8.21
KB
-rw-r--r--
2025-06-06 11:26
vtzone.h
20.68
KB
-rw-r--r--
2025-06-06 11:26
Save
Rename
// © 2016 and later: Unicode, Inc. and others. // License & terms of use: http://www.unicode.org/copyright.html /* ******************************************************************************* * * Copyright (C) 2009-2013, International Business Machines * Corporation and others. All Rights Reserved. * ******************************************************************************* * file name: normalizer2.h * encoding: UTF-8 * tab size: 8 (not used) * indentation:4 * * created on: 2009nov22 * created by: Markus W. Scherer */ #ifndef __NORMALIZER2_H__ #define __NORMALIZER2_H__ /** * \file * \brief C++ API: New API for Unicode Normalization. */ #include "unicode/utypes.h" #if U_SHOW_CPLUSPLUS_API #if !UCONFIG_NO_NORMALIZATION #include "unicode/stringpiece.h" #include "unicode/uniset.h" #include "unicode/unistr.h" #include "unicode/unorm2.h" U_NAMESPACE_BEGIN class ByteSink; /** * Unicode normalization functionality for standard Unicode normalization or * for using custom mapping tables. * All instances of this class are unmodifiable/immutable. * Instances returned by getInstance() are singletons that must not be deleted by the caller. * The Normalizer2 class is not intended for public subclassing. * * The primary functions are to produce a normalized string and to detect whether * a string is already normalized. * The most commonly used normalization forms are those defined in * http://www.unicode.org/unicode/reports/tr15/ * However, this API supports additional normalization forms for specialized purposes. * For example, NFKC_Casefold is provided via getInstance("nfkc_cf", COMPOSE) * and can be used in implementations of UTS #46. * * Not only are the standard compose and decompose modes supplied, * but additional modes are provided as documented in the Mode enum. * * Some of the functions in this class identify normalization boundaries. * At a normalization boundary, the portions of the string * before it and starting from it do not interact and can be handled independently. * * The spanQuickCheckYes() stops at a normalization boundary. * When the goal is a normalized string, then the text before the boundary * can be copied, and the remainder can be processed with normalizeSecondAndAppend(). * * The hasBoundaryBefore(), hasBoundaryAfter() and isInert() functions test whether * a character is guaranteed to be at a normalization boundary, * regardless of context. * This is used for moving from one normalization boundary to the next * or preceding boundary, and for performing iterative normalization. * * Iterative normalization is useful when only a small portion of a * longer string needs to be processed. * For example, in ICU, iterative normalization is used by the NormalizationTransliterator * (to avoid replacing already-normalized text) and ucol_nextSortKeyPart() * (to process only the substring for which sort key bytes are computed). * * The set of normalization boundaries returned by these functions may not be * complete: There may be more boundaries that could be returned. * Different functions may return different boundaries. * @stable ICU 4.4 */ class U_COMMON_API Normalizer2 : public UObject { public: /** * Destructor. * @stable ICU 4.4 */ ~Normalizer2(); /** * Returns a Normalizer2 instance for Unicode NFC normalization. * Same as getInstance(nullptr, "nfc", UNORM2_COMPOSE, errorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested Normalizer2, if successful * @stable ICU 49 */ static const Normalizer2 * getNFCInstance(UErrorCode &errorCode); /** * Returns a Normalizer2 instance for Unicode NFD normalization. * Same as getInstance(nullptr, "nfc", UNORM2_DECOMPOSE, errorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested Normalizer2, if successful * @stable ICU 49 */ static const Normalizer2 * getNFDInstance(UErrorCode &errorCode); /** * Returns a Normalizer2 instance for Unicode NFKC normalization. * Same as getInstance(nullptr, "nfkc", UNORM2_COMPOSE, errorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested Normalizer2, if successful * @stable ICU 49 */ static const Normalizer2 * getNFKCInstance(UErrorCode &errorCode); /** * Returns a Normalizer2 instance for Unicode NFKD normalization. * Same as getInstance(nullptr, "nfkc", UNORM2_DECOMPOSE, errorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested Normalizer2, if successful * @stable ICU 49 */ static const Normalizer2 * getNFKDInstance(UErrorCode &errorCode); /** * Returns a Normalizer2 instance for Unicode toNFKC_Casefold() normalization * which is equivalent to applying the NFKC_Casefold mappings and then NFC. * See https://www.unicode.org/reports/tr44/#NFKC_Casefold * * Same as getInstance(nullptr, "nfkc_cf", UNORM2_COMPOSE, errorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested Normalizer2, if successful * @stable ICU 49 */ static const Normalizer2 * getNFKCCasefoldInstance(UErrorCode &errorCode); /** * Returns a Normalizer2 instance for a variant of Unicode toNFKC_Casefold() normalization * which is equivalent to applying the NFKC_Simple_Casefold mappings and then NFC. * See https://www.unicode.org/reports/tr44/#NFKC_Simple_Casefold * * Same as getInstance(nullptr, "nfkc_scf", UNORM2_COMPOSE, errorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested Normalizer2, if successful * @stable ICU 74 */ static const Normalizer2 * getNFKCSimpleCasefoldInstance(UErrorCode &errorCode); /** * Returns a Normalizer2 instance which uses the specified data file * (packageName/name similar to ucnv_openPackage() and ures_open()/ResourceBundle) * and which composes or decomposes text according to the specified mode. * Returns an unmodifiable singleton instance. Do not delete it. * * Use packageName=nullptr for data files that are part of ICU's own data. * Use name="nfc" and UNORM2_COMPOSE/UNORM2_DECOMPOSE for Unicode standard NFC/NFD. * Use name="nfkc" and UNORM2_COMPOSE/UNORM2_DECOMPOSE for Unicode standard NFKC/NFKD. * Use name="nfkc_cf" and UNORM2_COMPOSE for Unicode standard NFKC_CF=NFKC_Casefold. * * @param packageName nullptr for ICU built-in data, otherwise application data package name * @param name "nfc" or "nfkc" or "nfkc_cf" or "nfkc_scf" or name of custom data file * @param mode normalization mode (compose or decompose etc.) * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested Normalizer2, if successful * @stable ICU 4.4 */ static const Normalizer2 * getInstance(const char *packageName, const char *name, UNormalization2Mode mode, UErrorCode &errorCode); /** * Returns the normalized form of the source string. * @param src source string * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return normalized src * @stable ICU 4.4 */ UnicodeString normalize(const UnicodeString &src, UErrorCode &errorCode) const { UnicodeString result; normalize(src, result, errorCode); return result; } /** * Writes the normalized form of the source string to the destination string * (replacing its contents) and returns the destination string. * The source and destination strings must be different objects. * @param src source string * @param dest destination string; its contents is replaced with normalized src * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return dest * @stable ICU 4.4 */ virtual UnicodeString & normalize(const UnicodeString &src, UnicodeString &dest, UErrorCode &errorCode) const = 0; /** * Normalizes a UTF-8 string and optionally records how source substrings * relate to changed and unchanged result substrings. * * Implemented completely for all built-in modes except for FCD. * The base class implementation converts to & from UTF-16 and does not support edits. * * @param options Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT and U_EDITS_NO_RESET. * @param src Source UTF-8 string. * @param sink A ByteSink to which the normalized UTF-8 result string is written. * sink.Flush() is called at the end. * @param edits Records edits for index mapping, working with styled text, * and getting only changes (if any). * The Edits contents is undefined if any error occurs. * This function calls edits->reset() first unless * options includes U_EDITS_NO_RESET. edits can be nullptr. * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @stable ICU 60 */ virtual void normalizeUTF8(uint32_t options, StringPiece src, ByteSink &sink, Edits *edits, UErrorCode &errorCode) const; /** * Appends the normalized form of the second string to the first string * (merging them at the boundary) and returns the first string. * The result is normalized if the first string was normalized. * The first and second strings must be different objects. * @param first string, should be normalized * @param second string, will be normalized * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return first * @stable ICU 4.4 */ virtual UnicodeString & normalizeSecondAndAppend(UnicodeString &first, const UnicodeString &second, UErrorCode &errorCode) const = 0; /** * Appends the second string to the first string * (merging them at the boundary) and returns the first string. * The result is normalized if both the strings were normalized. * The first and second strings must be different objects. * @param first string, should be normalized * @param second string, should be normalized * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return first * @stable ICU 4.4 */ virtual UnicodeString & append(UnicodeString &first, const UnicodeString &second, UErrorCode &errorCode) const = 0; /** * Gets the decomposition mapping of c. * Roughly equivalent to normalizing the String form of c * on a UNORM2_DECOMPOSE Normalizer2 instance, but much faster, and except that this function * returns false and does not write a string * if c does not have a decomposition mapping in this instance's data. * This function is independent of the mode of the Normalizer2. * @param c code point * @param decomposition String object which will be set to c's * decomposition mapping, if there is one. * @return true if c has a decomposition, otherwise false * @stable ICU 4.6 */ virtual UBool getDecomposition(UChar32 c, UnicodeString &decomposition) const = 0; /** * Gets the raw decomposition mapping of c. * * This is similar to the getDecomposition() method but returns the * raw decomposition mapping as specified in UnicodeData.txt or * (for custom data) in the mapping files processed by the gennorm2 tool. * By contrast, getDecomposition() returns the processed, * recursively-decomposed version of this mapping. * * When used on a standard NFKC Normalizer2 instance, * getRawDecomposition() returns the Unicode Decomposition_Mapping (dm) property. * * When used on a standard NFC Normalizer2 instance, * it returns the Decomposition_Mapping only if the Decomposition_Type (dt) is Canonical (Can); * in this case, the result contains either one or two code points (=1..4 char16_ts). * * This function is independent of the mode of the Normalizer2. * The default implementation returns false. * @param c code point * @param decomposition String object which will be set to c's * raw decomposition mapping, if there is one. * @return true if c has a decomposition, otherwise false * @stable ICU 49 */ virtual UBool getRawDecomposition(UChar32 c, UnicodeString &decomposition) const; /** * Performs pairwise composition of a & b and returns the composite if there is one. * * Returns a composite code point c only if c has a two-way mapping to a+b. * In standard Unicode normalization, this means that * c has a canonical decomposition to a+b * and c does not have the Full_Composition_Exclusion property. * * This function is independent of the mode of the Normalizer2. * The default implementation returns a negative value. * @param a A (normalization starter) code point. * @param b Another code point. * @return The non-negative composite code point if there is one; otherwise a negative value. * @stable ICU 49 */ virtual UChar32 composePair(UChar32 a, UChar32 b) const; /** * Gets the combining class of c. * The default implementation returns 0 * but all standard implementations return the Unicode Canonical_Combining_Class value. * @param c code point * @return c's combining class * @stable ICU 49 */ virtual uint8_t getCombiningClass(UChar32 c) const; /** * Tests if the string is normalized. * Internally, in cases where the quickCheck() method would return "maybe" * (which is only possible for the two COMPOSE modes) this method * resolves to "yes" or "no" to provide a definitive result, * at the cost of doing more work in those cases. * @param s input string * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return true if s is normalized * @stable ICU 4.4 */ virtual UBool isNormalized(const UnicodeString &s, UErrorCode &errorCode) const = 0; /** * Tests if the UTF-8 string is normalized. * Internally, in cases where the quickCheck() method would return "maybe" * (which is only possible for the two COMPOSE modes) this method * resolves to "yes" or "no" to provide a definitive result, * at the cost of doing more work in those cases. * * This works for all normalization modes. * It is optimized for UTF-8 for all built-in modes except for FCD. * The base class implementation converts to UTF-16 and calls isNormalized(). * * @param s UTF-8 input string * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return true if s is normalized * @stable ICU 60 */ virtual UBool isNormalizedUTF8(StringPiece s, UErrorCode &errorCode) const; /** * Tests if the string is normalized. * For the two COMPOSE modes, the result could be "maybe" in cases that * would take a little more work to resolve definitively. * Use spanQuickCheckYes() and normalizeSecondAndAppend() for a faster * combination of quick check + normalization, to avoid * re-checking the "yes" prefix. * @param s input string * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return UNormalizationCheckResult * @stable ICU 4.4 */ virtual UNormalizationCheckResult quickCheck(const UnicodeString &s, UErrorCode &errorCode) const = 0; /** * Returns the end of the normalized substring of the input string. * In other words, with <code>end=spanQuickCheckYes(s, ec);</code> * the substring <code>UnicodeString(s, 0, end)</code> * will pass the quick check with a "yes" result. * * The returned end index is usually one or more characters before the * "no" or "maybe" character: The end index is at a normalization boundary. * (See the class documentation for more about normalization boundaries.) * * When the goal is a normalized string and most input strings are expected * to be normalized already, then call this method, * and if it returns a prefix shorter than the input string, * copy that prefix and use normalizeSecondAndAppend() for the remainder. * @param s input string * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return "yes" span end index * @stable ICU 4.4 */ virtual int32_t spanQuickCheckYes(const UnicodeString &s, UErrorCode &errorCode) const = 0; /** * Tests if the character always has a normalization boundary before it, * regardless of context. * If true, then the character does not normalization-interact with * preceding characters. * In other words, a string containing this character can be normalized * by processing portions before this character and starting from this * character independently. * This is used for iterative normalization. See the class documentation for details. * @param c character to test * @return true if c has a normalization boundary before it * @stable ICU 4.4 */ virtual UBool hasBoundaryBefore(UChar32 c) const = 0; /** * Tests if the character always has a normalization boundary after it, * regardless of context. * If true, then the character does not normalization-interact with * following characters. * In other words, a string containing this character can be normalized * by processing portions up to this character and after this * character independently. * This is used for iterative normalization. See the class documentation for details. * Note that this operation may be significantly slower than hasBoundaryBefore(). * @param c character to test * @return true if c has a normalization boundary after it * @stable ICU 4.4 */ virtual UBool hasBoundaryAfter(UChar32 c) const = 0; /** * Tests if the character is normalization-inert. * If true, then the character does not change, nor normalization-interact with * preceding or following characters. * In other words, a string containing this character can be normalized * by processing portions before this character and after this * character independently. * This is used for iterative normalization. See the class documentation for details. * Note that this operation may be significantly slower than hasBoundaryBefore(). * @param c character to test * @return true if c is normalization-inert * @stable ICU 4.4 */ virtual UBool isInert(UChar32 c) const = 0; }; /** * Normalization filtered by a UnicodeSet. * Normalizes portions of the text contained in the filter set and leaves * portions not contained in the filter set unchanged. * Filtering is done via UnicodeSet::span(..., USET_SPAN_SIMPLE). * Not-in-the-filter text is treated as "is normalized" and "quick check yes". * This class implements all of (and only) the Normalizer2 API. * An instance of this class is unmodifiable/immutable but is constructed and * must be destructed by the owner. * @stable ICU 4.4 */ class U_COMMON_API FilteredNormalizer2 : public Normalizer2 { public: /** * Constructs a filtered normalizer wrapping any Normalizer2 instance * and a filter set. * Both are aliased and must not be modified or deleted while this object * is used. * The filter set should be frozen; otherwise the performance will suffer greatly. * @param n2 wrapped Normalizer2 instance * @param filterSet UnicodeSet which determines the characters to be normalized * @stable ICU 4.4 */ FilteredNormalizer2(const Normalizer2 &n2, const UnicodeSet &filterSet) : norm2(n2), set(filterSet) {} /** * Destructor. * @stable ICU 4.4 */ ~FilteredNormalizer2(); /** * Writes the normalized form of the source string to the destination string * (replacing its contents) and returns the destination string. * The source and destination strings must be different objects. * @param src source string * @param dest destination string; its contents is replaced with normalized src * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return dest * @stable ICU 4.4 */ virtual UnicodeString & normalize(const UnicodeString &src, UnicodeString &dest, UErrorCode &errorCode) const override; /** * Normalizes a UTF-8 string and optionally records how source substrings * relate to changed and unchanged result substrings. * * Implemented completely for most built-in modes except for FCD. * The base class implementation converts to & from UTF-16 and does not support edits. * * @param options Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT and U_EDITS_NO_RESET. * @param src Source UTF-8 string. * @param sink A ByteSink to which the normalized UTF-8 result string is written. * sink.Flush() is called at the end. * @param edits Records edits for index mapping, working with styled text, * and getting only changes (if any). * The Edits contents is undefined if any error occurs. * This function calls edits->reset() first unless * options includes U_EDITS_NO_RESET. edits can be nullptr. * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @stable ICU 60 */ virtual void normalizeUTF8(uint32_t options, StringPiece src, ByteSink &sink, Edits *edits, UErrorCode &errorCode) const override; /** * Appends the normalized form of the second string to the first string * (merging them at the boundary) and returns the first string. * The result is normalized if the first string was normalized. * The first and second strings must be different objects. * @param first string, should be normalized * @param second string, will be normalized * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return first * @stable ICU 4.4 */ virtual UnicodeString & normalizeSecondAndAppend(UnicodeString &first, const UnicodeString &second, UErrorCode &errorCode) const override; /** * Appends the second string to the first string * (merging them at the boundary) and returns the first string. * The result is normalized if both the strings were normalized. * The first and second strings must be different objects. * @param first string, should be normalized * @param second string, should be normalized * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return first * @stable ICU 4.4 */ virtual UnicodeString & append(UnicodeString &first, const UnicodeString &second, UErrorCode &errorCode) const override; /** * Gets the decomposition mapping of c. * For details see the base class documentation. * * This function is independent of the mode of the Normalizer2. * @param c code point * @param decomposition String object which will be set to c's * decomposition mapping, if there is one. * @return true if c has a decomposition, otherwise false * @stable ICU 4.6 */ virtual UBool getDecomposition(UChar32 c, UnicodeString &decomposition) const override; /** * Gets the raw decomposition mapping of c. * For details see the base class documentation. * * This function is independent of the mode of the Normalizer2. * @param c code point * @param decomposition String object which will be set to c's * raw decomposition mapping, if there is one. * @return true if c has a decomposition, otherwise false * @stable ICU 49 */ virtual UBool getRawDecomposition(UChar32 c, UnicodeString &decomposition) const override; /** * Performs pairwise composition of a & b and returns the composite if there is one. * For details see the base class documentation. * * This function is independent of the mode of the Normalizer2. * @param a A (normalization starter) code point. * @param b Another code point. * @return The non-negative composite code point if there is one; otherwise a negative value. * @stable ICU 49 */ virtual UChar32 composePair(UChar32 a, UChar32 b) const override; /** * Gets the combining class of c. * The default implementation returns 0 * but all standard implementations return the Unicode Canonical_Combining_Class value. * @param c code point * @return c's combining class * @stable ICU 49 */ virtual uint8_t getCombiningClass(UChar32 c) const override; /** * Tests if the string is normalized. * For details see the Normalizer2 base class documentation. * @param s input string * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return true if s is normalized * @stable ICU 4.4 */ virtual UBool isNormalized(const UnicodeString &s, UErrorCode &errorCode) const override; /** * Tests if the UTF-8 string is normalized. * Internally, in cases where the quickCheck() method would return "maybe" * (which is only possible for the two COMPOSE modes) this method * resolves to "yes" or "no" to provide a definitive result, * at the cost of doing more work in those cases. * * This works for all normalization modes. * It is optimized for UTF-8 for all built-in modes except for FCD. * The base class implementation converts to UTF-16 and calls isNormalized(). * * @param s UTF-8 input string * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return true if s is normalized * @stable ICU 60 */ virtual UBool isNormalizedUTF8(StringPiece s, UErrorCode &errorCode) const override; /** * Tests if the string is normalized. * For details see the Normalizer2 base class documentation. * @param s input string * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return UNormalizationCheckResult * @stable ICU 4.4 */ virtual UNormalizationCheckResult quickCheck(const UnicodeString &s, UErrorCode &errorCode) const override; /** * Returns the end of the normalized substring of the input string. * For details see the Normalizer2 base class documentation. * @param s input string * @param errorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return "yes" span end index * @stable ICU 4.4 */ virtual int32_t spanQuickCheckYes(const UnicodeString &s, UErrorCode &errorCode) const override; /** * Tests if the character always has a normalization boundary before it, * regardless of context. * For details see the Normalizer2 base class documentation. * @param c character to test * @return true if c has a normalization boundary before it * @stable ICU 4.4 */ virtual UBool hasBoundaryBefore(UChar32 c) const override; /** * Tests if the character always has a normalization boundary after it, * regardless of context. * For details see the Normalizer2 base class documentation. * @param c character to test * @return true if c has a normalization boundary after it * @stable ICU 4.4 */ virtual UBool hasBoundaryAfter(UChar32 c) const override; /** * Tests if the character is normalization-inert. * For details see the Normalizer2 base class documentation. * @param c character to test * @return true if c is normalization-inert * @stable ICU 4.4 */ virtual UBool isInert(UChar32 c) const override; private: UnicodeString & normalize(const UnicodeString &src, UnicodeString &dest, USetSpanCondition spanCondition, UErrorCode &errorCode) const; void normalizeUTF8(uint32_t options, const char *src, int32_t length, ByteSink &sink, Edits *edits, USetSpanCondition spanCondition, UErrorCode &errorCode) const; UnicodeString & normalizeSecondAndAppend(UnicodeString &first, const UnicodeString &second, UBool doNormalize, UErrorCode &errorCode) const; const Normalizer2 &norm2; const UnicodeSet &set; }; U_NAMESPACE_END #endif // !UCONFIG_NO_NORMALIZATION #endif /* U_SHOW_CPLUSPLUS_API */ #endif // __NORMALIZER2_H__